
To address the low efficiency and high flower bud damage rate in camellia-fruit-picking machines, a multichannel camellia-fruit-picking device was designed. Three factors and levels of the quadratic orthogonal rotation combination test method were used in the test. The experimental results show that the fruit picking and bud damage rates were affected most by the roller speed, followed by the distance between rollers, and, finally, the roller diameter. The optimal parameter combination was determined to be the roller speed of 130 mm/s, distance between rollers of 21 mm, and roller diameter of 30 mm, as verified by outdoor experiments. The average camellia-fruit-picking and bud damage rates were 95.68% and 3.92%, respectively. Compared with a rotating rubber roller picking device, the average flower bud damage rate of the multichannel camellia-fruit-picking device was reduced by 14.71 percentage points.
In response to the problems of labor-intensive and inefficient manual cleaning of land-based factory aquaculture ponds, this paper designs an automatic cleaning robot for aquaculture ponds based on rail movement and with the function of over-pond cleaning. The robot consists of moving mechanism, a cleaning mechanism, and a control system. The moving mechanism moves backwards and forwards, left and right along the rails above the pond, the cleaning mechanism cleans the bottom and wall of the pond by rotating and telescoping up and down, and the control system realizes the precise control of the cleaning robot by means of an STM32F103 microcontroller. Path planning is carried out by establishing a full-coverage raster map, and automatic obstacle avoidance is achieved by using algorithms such as shortest tangent and wildfire method.
为研究日光温室内环境要素对番茄果期生长发育的影响,探究环境要素与番茄果实生长发育的量化关系.基于山东省德州市陵城区糜镇智慧农业产业园日光温室秋冬茬番茄果期生长数据和环境数据,分析数据间的相关性和多重共线性,采用逐步回归和主成分回归组合方法,构建设施番茄果期生长模型.结果表明:果实横径与各环境因子累计量存在较强的线性相关关系,果实横径与各环境因子(空气温度、空气湿度、光照强度、CO2 浓度、土壤温度)累计量的相关系数分别为0.96、0.95、0.95、0.94、0.94.温室内环境因子间存在较强的多重共线性,通过逐步回归分析出3个显著环境因子:空气温度、光照强度和CO2 浓度.通过主成分回归建立的设施番茄果期生长模型确定系数为0.93,拟合效果较好.
为满足实际种植环境下对病害叶片精准用药的需求,以设施环境复杂背景图像为研究对象,提出基于语义分割的复杂背景下黄瓜叶部病害分级方法.首先,使用Labelme标注软件对图像叶片和病斑进行标注,并对部分病害叶片进行图像增强以丰富数据集;然后,改进U-Net网络结构并构建基于深度学习的复杂背景下黄瓜叶片病害分割两阶段架构,对复杂背景下的黄瓜叶片、病斑进行分割;最后,提出黄瓜霜霉病、炭疽病病害严重程度分级模型D-MUNet,对病害等级进行划分.改进后的U-Net模型像素精度、平均交并比和Dice系数分别为90.48%、92.46%、0.6457,较原始模型提升2.36%、2.34%和0.0238.黄瓜霜霉病、炭疽病病害分级准确率分别达到92.11%和89.17%.基于语义分割的复杂背景下黄瓜叶部病害严重程度分级方法,能够对黄瓜病害实现有效地分割、分级,为病害的精准防治提供技术支撑.
为促进设施蔬菜生产机械化,针对设施蔬菜生产中"开种植沟、沟内施肥、覆土稳沟"的农艺要求,设计一种设施蔬菜生产无人开沟施肥机.该机由行驶底盘系统、开沟施肥作业系统、液压传动系统、自动控制系统、供电系统等组成,一次可完成开沟、施肥、覆土、稳沟等作业4~6行.作业时,由手机 APP经过运营商的 NB-IoT与该机上的PLC通信,并由PLC控制柴油发动机启停及液压传动系统工作,再由液压传动系统驱动整机行驶及开沟施肥作业.设计过程中,通过UG软件对该机进行三维建模并对主要受力部件进行结构强度分析,得出机架的刚度需适当加强.田间试验结果表明:开沟施肥深度90~130mm、肥料细碎匀混度≥90%、施肥均匀度≥90%、覆土厚度≥50mm,沟底土面宽度约100mm、沟底土面深度30~70mm、沟形稳固度≥95%,持续施肥时长≥1个大棚,远程控制距离≥2km,即各项指标符合设计要求.该研究对提高设施蔬菜生产中开沟施肥作业的质量和效率、降低劳动强度和劳动成本,有着重要意义.